Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    government, laws, and jail

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (environment
    -0.06
    983
    -0.06
    桂
    -0.06
    ">'↵
    -0.06
    English
    -0.06
     สพ
    -0.06
     condemnation
    -0.06
    Ｏ
    -0.06
     automated
    -0.06
    DataGridView
    -0.06
    POSITIVE LOGITS
    rovers
    0.08
    =%
    0.07
     downtime
    0.07
     за
    0.06
     getPage
    0.06
    럭
    0.06
     khoán
    0.06
    ươ
    0.06
    ยน
    0.06
    ,top
    0.06
    Act Density 0.202%

    No Known Activations